Image Encryption Technology Research Based on Neural Network

Digital image parallel encryption structure based on cellular neural network is proposed to improve the efficiency and security, where the properties of parallel computing and local diffusion of cellular neural network are utilized effectively. A kind of group encryption algorithm based on feistel framework is put forward. In each round, a cell encrypts one block image data with block encryption algorithm firstly, and then affected by the output of 8-neighbouring cells. Then the image encryption algorithm is effectively strengthened by raius basis chaos neural network. The experiment results show the proposed algorithm has good effect.